|
--- |
|
tags: |
|
- lightblue/karasu-1.1B |
|
- yuiseki/karasu-sake-qa-v0.1 |
|
language: |
|
- ja |
|
- en |
|
--- |
|
# karasu-lora-jp-qa-chat |
|
|
|
karasu fine tuned model by lora method with the original Q&A dataset. |
|
This model is usefull for rag system with reference input files. |
|
* Base model: Merged model of lightblue/karasu-1.1B and yuiseki/karasu-sake-qa-v0.1 (aipib/karasu-slerp1) |
|
* Traning dataset: Original japanese question and answer lists |
|
|
|
## 💻 Usage |
|
|
|
```python |
|
!pip install -qU transformers accelerate |
|
|
|
from transformers import AutoTokenizer |
|
import transformers |
|
import torch |
|
|
|
model = "aipib/suzume-taskarith1" |
|
messages = [{"role": "user", "content": "What is a large language model?"}] |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model) |
|
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) |
|
pipeline = transformers.pipeline( |
|
"text-generation", |
|
model=model, |
|
torch_dtype=torch.float16, |
|
device_map="auto", |
|
) |
|
|
|
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) |
|
print(outputs[0]["generated_text"]) |
|
``` |
